<html><head><meta http-equiv="Content-Type" content="text/html charset=utf-8"></head><body style="word-wrap: break-word; -webkit-nbsp-mode: space; -webkit-line-break: after-white-space; "><div>Hello Amy,</div><div><br></div><div>If you're using C/C++ I recommend having a look at MeCab (<a href="https://code.google.com/p/mecab/">https://code.google.com/p/mecab/</a>). If you're using Java, you might find Kuromoji (<a href="http://atilika.org/">http://atilika.org/</a>) useful, which has almost identical segmentation as MeCab (middle dot is treated somewhat differently).</div><div><br></div><div>There's to my knowledge no freely available statistical model trained exclusively on tweets (similar to CMU ARK's TweetNLP) for Japanese. However, UniDic is based on a balanced corpus and I'd start experimenting with that model/dictionary. Please feel free to get in touch directly if you need help getting started with Kuromoji.</div><div><br></div><div>Best regards,</div><div><br></div><div>Christian Moen</div><div>アティリカ株式会社</div><div><a href="http://www.atilika.com">http://www.atilika.com</a></div><div><br></div><div><div>On Sep 15, 2013, at 3:26 AM, Amy Aisha Brown <<a href="mailto:amy-aisha.brown@open.ac.uk">amy-aisha.brown@open.ac.uk</a>> wrote:</div><br class="Apple-interchange-newline"><blockquote type="cite"><div dir="ltr">Dear all,<br><div><br></div><div>This is a long shot but I am looking for a POS tagging/morphological analysis system for Japanese that works (well) with tweets (i.e., something that has been trained with social media texts).</div>
<div><br></div><div>If anyone has any information about this, I would love to hear from you.</div><div><br></div><div>Thanks in advance!</div><div><br></div><div>Amy Brown<br clear="all"><div><br></div>-- <br><div dir="ltr">
Amy Aisha Brown</div><div dir="ltr">Research Student<div><div>Faculty of Education and Language Studies</div><div>The Open University</div><div><a href="mailto:amy-aisha.brown@open.ac.uk">amy-aisha.brown@open.ac.uk</a></div>
</div></div>
</div></div>
_______________________________________________<br>UNSUBSCRIBE from this page: <a href="http://mailman.uib.no/options/corpora">http://mailman.uib.no/options/corpora</a><br>Corpora mailing list<br><a href="mailto:Corpora@uib.no">Corpora@uib.no</a><br>http://mailman.uib.no/listinfo/corpora<br></blockquote></div><br></body></html>